Convolutional Neural Networks in Bird Classification¶

Let's import the necessary libraries.

In [1]:
# import the needed packages
import pandas as pd
import tensorflow as tf
import matplotlib.pyplot as plt
import matplotlib.image as img
import tensorflow.keras as keras
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping
from random import choice
from random import uniform
from numpy.random import randint
from statistics import mean
In [3]:
# Load the TensorBoard notebook extension
%load_ext tensorboard
from tensorflow.keras.models import Sequential, Model, load_model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization, Activation
from tensorflow.keras import optimizers
from tensorflow.keras.optimizers import RMSprop

The tensorboard extension is already loaded. To reload it, use:
  %reload_ext tensorboard
In [10]:
#train, validation and test directories

training_dir = 'C:/Users/MAK/Downloads/bird-species-classification-main/bird-species-classification-main/dataset/train'
validation_dir = 'C:/Users/MAK/Downloads/bird-species-classification-main/bird-species-classification-main/dataset/valid'
test_dir = 'C:/Users/MAK/Downloads/bird-species-classification-main/bird-species-classification-main/dataset/test'

Analysing the Dataset¶

Let's start by importing the training and validation datasets.

In [11]:
train_datagen = ImageDataGenerator(rescale=1/255)
validation_datagen = ImageDataGenerator(rescale=1/255)
test_datagen = ImageDataGenerator(rescale=1/255)

def generate_datasets(bs, train_datag):
  train_generator = train_datag.flow_from_directory(
      training_dir,  
      target_size = (224,224), 
      color_mode = 'rgb',
      class_mode = 'sparse',
      batch_size = bs)

  validation_generator = validation_datagen.flow_from_directory(
      validation_dir, 
      target_size = (224,224),
      color_mode = 'rgb',
      class_mode = 'sparse',
      batch_size = bs)

  test_generator = validation_datagen.flow_from_directory(
      test_dir, 
      target_size = (224,224),
      color_mode = 'rgb',
      class_mode = 'sparse',
      batch_size = bs)
  
  return train_generator, validation_generator, test_generator

Let's now analyze the training dataset.

In [12]:
train_generator, validation_generator, test_generator = generate_datasets(16, train_datagen)

Found 35215 images belonging to 250 classes.
Found 1250 images belonging to 250 classes.
Found 1250 images belonging to 250 classes.
In [13]:
#map indexes in classes names
class_mapping = {v:k for k,v in train_generator.class_indices.items()}

defining a function to display some images from the dataset in a grid for better visualization.¶

In [14]:
from matplotlib import cm
from mpl_toolkits.axes_grid1 import ImageGrid
import math
%matplotlib inline

#function from: https://expoundai.wordpress.com/2019/04/24/image-data-generators-in-keras/
def show_grid(image_list, nrows, ncols, label_list = None, show_labels = False, savename = None, figsize = (10,10), showaxis = 'off'):

    if type(image_list) is not list:
        if(image_list.shape[-1] == 1):
            image_list = [image_list[i, :, :, 0] for i in range(image_list.shape[0])]
        elif(image_list.shape[-1] == 3):
            image_list = [image_list[i, :, :, :] for i in range(image_list.shape[0])]
    fig = plt.figure(None, figsize, frameon = False)

    grid = ImageGrid(fig, 111,  # similar to subplot(111)
                     nrows_ncols = (nrows, ncols),  # creates 2x2 grid of axes
                     axes_pad = 0.3,  # pad between axes in inch.
                     share_all = True,
                     )
    
    for i in range(nrows * ncols):
        ax = grid[i]
        ax.imshow(image_list[i], cmap='Greys_r')  # The AxesGrid object work as a list of axes.
        ax.axis('off')
        if show_labels:
            ax.set_title(class_mapping[y[i]])
    if savename != None:
        plt.savefig(savename, bbox_inches = 'tight')
In [15]:
for i in range(4):
  x, y = train_generator.next()
  show_grid(x, 2, 8, label_list = y, show_labels = True, figsize = (20,10))

The analyze_dataset function builds a graph that analyzes the number of images of each class in the dataset passed as a parameter.

In [16]:
def analyze_dataset(train_gen):
  #count the number of images of each class
  unique, counts = np.unique(train_gen.classes, return_counts=True)
  d = dict(zip(unique, counts))
  #print(d)
  print("Classe with less images: ", min(d.items(), key=lambda x: x[1] ))
  print("Classe with more images: ", max(d.items(), key=lambda x: x[1] ))
  print("Mean of images: ", mean(d[k] for k in d))

  #presenting the number of images of each class in a plot
  plt.figure(figsize=(20, 5))
  plt.bar(d.keys(), d.values(), width = 1.2, color = ['paleturquoise', 'yellow', 'orange'])
  plt.xlabel('Classes')
  plt.ylabel('Number of images per class')
  plt.show()
In [17]:
analyze_dataset(train_generator)

Classe with less images:  (194, 95)
Classe with more images:  (210, 300)
Mean of images:  140

Image Augmentation¶

In [18]:
train_datagen_aug = ImageDataGenerator(rescale=1/255,
                                   rotation_range=20,
                                   width_shift_range=0.2,
                                   height_shift_range=0.2)

train_generator_aug, _, _ = generate_datasets(16, train_datagen_aug)

Found 35215 images belonging to 250 classes.
Found 1250 images belonging to 250 classes.
Found 1250 images belonging to 250 classes.

CNN model definition for multiple classes¶

This model consists of a first approach to the problem.

In [36]:
import datetime
import tensorflow as tf
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, BatchNormalization

start = datetime.datetime.now()

# Example values for the function parameters
n_layers = 2
bs = 32
op = 'adam'
ep = 10

# Example directory paths to training and validation data
training_dir = 'C:/Users/MAK/Downloads/bird-species-classification-main/bird-species-classification-main/dataset/train'
validation_dir = 'C:/Users/MAK/Downloads/bird-species-classification-main/bird-species-classification-main/dataset/valid'

# Initialize ImageDataGenerator for training and validation data
train_datagen = tf.keras.preprocessing.image.ImageDataGenerator(
    rescale=1./255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

validation_datagen = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255)

# Flow training images in batches of 32 using train_datagen generator
train_generator = train_datagen.flow_from_directory(
    training_dir,
    target_size=(224, 224),
    batch_size=bs,
    class_mode='categorical')

# Flow validation images in batches of 32 using validation_datagen generator
validation_generator = validation_datagen.flow_from_directory(
    validation_dir,
    target_size=(224, 224),
    batch_size=bs,
    class_mode='categorical')

def CNN_model(n_layers, bs, op, ep, train_generator, validation_generator):
    model = tf.keras.models.Sequential([
        Conv2D(128, (3,3), activation='relu', input_shape=(224, 224, 3)),
        MaxPooling2D(2, 2),
        Conv2D(128, (3,3), activation='relu'),
        MaxPooling2D(2,2),
        Conv2D(64, (3,3), activation='relu'),
        MaxPooling2D(2,2),
        Conv2D(32, (3,3), activation='relu'),
        MaxPooling2D(2,2),
        BatchNormalization(momentum=0.9),
        Conv2D(16, (3,3), activation='relu'),
        MaxPooling2D(2,2),
        Flatten()
    ])
      
    # Dense layers
    for i in range(n_layers):
        model.add(Dense(512, activation='relu'))

    model.add(Dense(250, activation='softmax'))

    model.summary()

    # Compile
    model.compile(loss='categorical_crossentropy',
                  optimizer= op,
                  metrics=['acc'])

    # Fit
    history = model.fit_generator(
        train_generator,
        steps_per_epoch=8,  
        epochs= ep,
        verbose=1,
        validation_data = validation_generator,
        validation_steps = 8
    )
    model.save('model.h5')

    return model, history

# Run the function with example values
trained_model, training_history = CNN_model(n_layers, bs, op, ep, train_generator, validation_generator)

end = datetime.datetime.now()
print("Total time taken: ", end-start)



#CNN_model(2, 32, "adam", 50)

Found 35215 images belonging to 250 classes.
Found 1250 images belonging to 250 classes.
Model: "sequential_7"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_35 (Conv2D)           (None, 222, 222, 128)     3584      
_________________________________________________________________
max_pooling2d_35 (MaxPooling (None, 111, 111, 128)     0         
_________________________________________________________________
conv2d_36 (Conv2D)           (None, 109, 109, 128)     147584    
_________________________________________________________________
max_pooling2d_36 (MaxPooling (None, 54, 54, 128)       0         
_________________________________________________________________
conv2d_37 (Conv2D)           (None, 52, 52, 64)        73792     
_________________________________________________________________
max_pooling2d_37 (MaxPooling (None, 26, 26, 64)        0         
_________________________________________________________________
conv2d_38 (Conv2D)           (None, 24, 24, 32)        18464     
_________________________________________________________________
max_pooling2d_38 (MaxPooling (None, 12, 12, 32)        0         
_________________________________________________________________
batch_normalization_7 (Batch (None, 12, 12, 32)        128       
_________________________________________________________________
conv2d_39 (Conv2D)           (None, 10, 10, 16)        4624      
_________________________________________________________________
max_pooling2d_39 (MaxPooling (None, 5, 5, 16)          0         
_________________________________________________________________
flatten_7 (Flatten)          (None, 400)               0         
_________________________________________________________________
dense_21 (Dense)             (None, 512)               205312    
_________________________________________________________________
dense_22 (Dense)             (None, 512)               262656    
_________________________________________________________________
dense_23 (Dense)             (None, 250)               128250    
=================================================================
Total params: 844,394
Trainable params: 844,330
Non-trainable params: 64
_________________________________________________________________
Epoch 1/10
8/8 [==============================] - 5s 565ms/step - loss: 5.5963 - acc: 0.0078 - val_loss: 5.5046 - val_acc: 0.0117
Epoch 2/10
8/8 [==============================] - 4s 477ms/step - loss: 5.5649 - acc: 0.0000e+00 - val_loss: 5.5362 - val_acc: 0.0078
Epoch 3/10
8/8 [==============================] - 4s 473ms/step - loss: 5.5713 - acc: 0.0039 - val_loss: 5.5268 - val_acc: 0.0000e+00
Epoch 4/10
8/8 [==============================] - 4s 481ms/step - loss: 5.5187 - acc: 0.0117 - val_loss: 5.5166 - val_acc: 0.0039
Epoch 5/10
8/8 [==============================] - 4s 475ms/step - loss: 5.5049 - acc: 0.0039 - val_loss: 5.5245 - val_acc: 0.0039
Epoch 6/10
8/8 [==============================] - 4s 462ms/step - loss: 5.4842 - acc: 0.0156 - val_loss: 5.5002 - val_acc: 0.0039
Epoch 7/10
8/8 [==============================] - 4s 466ms/step - loss: 5.4994 - acc: 0.0000e+00 - val_loss: 5.5066 - val_acc: 0.0117
Epoch 8/10
8/8 [==============================] - 4s 465ms/step - loss: 5.5004 - acc: 0.0195 - val_loss: 5.4869 - val_acc: 0.0117
Epoch 9/10
8/8 [==============================] - 4s 463ms/step - loss: 5.4633 - acc: 0.0156 - val_loss: 5.4141 - val_acc: 0.0156
Epoch 10/10
8/8 [==============================] - 4s 461ms/step - loss: 5.4548 - acc: 0.0117 - val_loss: 5.4195 - val_acc: 0.0000e+00
Total time taken:  0:00:41.902702

Let's now train the model.

The plot_metrics function, defined below, creates graphs relating to the values ​​of the metrics to be analyzed.

In [37]:
def plot_metrics(history):  
  # summarize history for accuracy
  plt.plot(history.history['accuracy'])
  plt.plot(history.history['val_accuracy'])
  plt.title('model accuracy')
  plt.ylabel('accuracy')
  plt.xlabel('epoch')
  plt.legend(['train', 'test'], loc='upper left')
  plt.show()
  # summarize history for loss
  plt.plot(history.history['loss'])
  plt.plot(history.history['val_loss'])
  plt.title('model loss')
  plt.ylabel('loss')
  plt.xlabel('epoch')
  plt.legend(['train', 'test'], loc='upper left')
  plt.show()

Genetic Algorithm¶

In order to automate the process of optimizing the hyperparameters of a CNN model, whether developed from scratch or using transfer learning, a genetic algorithm was defined.

Each chromosome will take into account the hyperparameters that are intended to be evaluated in the network. Namely, the learning rate, the optimization function used and the learning rate value.

To select the best model, we will only use 5 epochs for each one.

In [38]:
#list of the possible values for each chromosome
lr_values = [0.1, 0.01, 0.001, 0.0001]
op_values = ["adamax", "adadelta", "adam", "adagrad", "sgd"]
bs_values = [8, 16, 32]
activ_values = ['elu', 'relu', 'tanh']

'''
Function that defines a chromosome
'''
def create_individual():  
  parameters = {}

  lr = choice(lr_values)
  parameters["lr"] = lr
  
  bs = choice(bs_values)
  parameters["bs"] = bs

  activ = choice(activ_values)
  parameters["activ"] = activ
  
  op = choice(op_values)
  parameters["op"] = op
  
  #ep = randint(50, 100)
  #parameters["ep"] = ep
  
  return parameters


'''
Function responsible for generating the population
'''
def generate_population(n):
  population = []

  for i in range(n):
    chromosome = create_individual()
    population.append(chromosome)
  return population


'''
Fitness function based on accuracy and loss
''' 
def fitness_evaluation(history):
  acc = max(history.history['accuracy'])
  loss = max(history.history['loss'])
  print("ACC ", acc)
  print("LOSS ", loss)
  return 0.8 * acc - 0.2 * loss


'''
Selection function based on the roulette wheel method (from: https://github.com/KrishnaManmayi/Hyper-Parameter-Optimization-of-CNN-using-genetic-algorithm/blob/main/Optimization_using_genetic_algorithm_Cifar10_using_CNN.ipynb)
'''
# Roulette wheel selection method
def selection(population_fitness):
  total = sum(population_fitness)
  percentage = [round((x/total) * 100) for x in population_fitness]
  selection_wheel = []
  for pop_index,num in enumerate(percentage):
    selection_wheel.extend([pop_index]*num)
  parent1_ind = choice(selection_wheel)
  parent2_ind = choice(selection_wheel)
  return [parent1_ind, parent2_ind]

'''
Function responsible for crossover. Random select gene from one of the two parents
'''
def crossover(parent1, parent2):
  child1 = {}
  child2 = {}

  child1["lr"] = choice([parent1["lr"], parent2["lr"]])
  child2["lr"] = choice([parent1["lr"], parent2["lr"]])

  child1["bs"] = choice([parent1["bs"], parent2["bs"]])
  child2["bs"] = choice([parent1["bs"], parent2["bs"]])

  child1["op"] = parent2["op"]
  child2["op"] = parent1["op"]

  child1["activ"] = parent1["activ"]
  child2["activ"] = parent2["activ"]
  return [child1, child2]


'''
Function responsible for mutation that swaps a random gene of a chromosome
'''
def mutation(chromosome):
  #select random gene to mutate
  m = randint(0,4)
  if m == 0:
    chromosome["lr"] = choice([x for x in lr_values if x != chromosome['lr']])

  elif m == 1:
    chromosome["op"] = choice([x for x in op_values if x != chromosome['op']])

  elif m == 2:
    chromosome["activ"] = choice([x for x in activ_values if x != chromosome['activ']])
  
  elif m == 3:
    chromosome["bs"] = choice([x for x in bs_values if x != chromosome['bs']])
  
  return chromosome
In [94]:
import datetime
import tensorflow as tf
from tensorflow.keras.layers import Dense
from tensorflow.keras.applications import ResNet101V2

# Define the ResNet101V2_model function
def ResNet101V2_model(n_layers, activation, optimizer, learning_rate, epochs):
    # Load the ResNet101V2 model without the top (fully connected) layers
    base_model = ResNet101V2(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
    
    # Freeze the convolutional base
    base_model.trainable = False
    
    # Create a new model on top
    model = tf.keras.Sequential([
        base_model,
        tf.keras.layers.GlobalAveragePooling2D(),
        tf.keras.layers.Dense(1024, activation=activation),
        tf.keras.layers.Dense(512, activation=activation),
        tf.keras.layers.Dense(250, activation='softmax')  # Output layer with 250 units and softmax activation
    ])
    
    # Compile the model
    model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=learning_rate),
                  loss='categorical_crossentropy',
                  metrics=['accuracy'])
    
    return model

# Example values for the function parameters
n_layers = 2
activation = 'relu'
optimizer = 'adam'
learning_rate = 0.001
epochs = 1

# Call the ResNet101V2_model function
model = ResNet101V2_model(n_layers, activation, optimizer, learning_rate, epochs)
In [43]:
# Call the ResNet101V2_model function to get the model
model = ResNet101V2_model(8, 'elu', 'adam', 0.001, 1)

# Fit the model to obtain the training history
history = model.fit(train_generator, validation_data=validation_generator, epochs=epochs)

# Evaluate the model's performance or do any other post-training operations
acc = fitness_evaluation(history)

1101/1101 [==============================] - 465s 415ms/step - loss: 1.2584 - accuracy: 0.6943 - val_loss: 0.4704 - val_accuracy: 0.8544
ACC  0.6943348050117493
LOSS  1.2583703994750977
In [44]:
print(history.history)
acc = fitness_evaluation(history)
plot_metrics(history)

{'loss': [1.2583703994750977], 'accuracy': [0.6943348050117493], 'val_loss': [0.47042959928512573], 'val_accuracy': [0.8543999791145325]}
ACC  0.6943348050117493
LOSS  1.2583703994750977

VGG16 model definition¶

In [47]:
import datetime
start = datetime.datetime.now()
num_classes = 250

def VGG16_model(op):
  # loading the weights of VGG16 without the top layer. These weights are trained on Imagenet dataset.
  vgg = tf.keras.applications.VGG16(input_shape = IMAGE_SIZE + [3], weights = 'imagenet', include_top = False)  # input_shape = (64,64,3) as required by VGG

  # this will exclude the initial layers from training phase as there are already been trained.
  for layer in vgg.layers:
      layer.trainable = False

  x = Flatten()(vgg.output)
  #x = Dense(128, activation = 'relu')(x)   # we can add a new fully connected layer but it will increase the execution time.
  x = Dense(num_classes, activation = 'softmax')(x)  # adding the output layer with softmax function as this is a multi label classification problem.

  model = Model(inputs = vgg.input, outputs = x)

  model.compile(loss='categorical_crossentropy', optimizer= op, metrics=['accuracy'])
  end= datetime.datetime.now()
  elapsed= end-start
  print ('Time: ', elapsed)
In [48]:
model.summary()

Model: "sequential_10"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
resnet101v2 (Functional)     (None, 7, 7, 2048)        42626560  
_________________________________________________________________
global_average_pooling2d_2 ( (None, 2048)              0         
_________________________________________________________________
dense_30 (Dense)             (None, 1024)              2098176   
_________________________________________________________________
dense_31 (Dense)             (None, 512)               524800    
_________________________________________________________________
dense_32 (Dense)             (None, 250)               128250    
=================================================================
Total params: 45,377,786
Trainable params: 2,751,226
Non-trainable params: 42,626,560
_________________________________________________________________

ResNet50 Model Definition¶

In [50]:
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, TensorBoard
from datetime import datetime
from tensorflow.keras.applications import resnet50

def ResNet50_model(op, ep):

  es = EarlyStopping(monitor='val_loss', patience=5)
  mc = ModelCheckpoint('best_model.h5', monitor='val_loss', mode='min', save_best_only=True)

  start = datetime.now()
  conv_model = resnet50.ResNet50(weights='imagenet', include_top=False, input_shape=(224,224,3))
  for layer in conv_model.layers:
      layer.trainable = False
  x = keras.layers.Flatten()(conv_model.output)
  x = keras.layers.Dense(100, activation='relu')(x)
  x = keras.layers.Dense(100, activation='relu')(x)
  x = keras.layers.Dense(100, activation='relu')(x)
  predictions = keras.layers.Dense(250, activation='softmax')(x)
  full_model = keras.models.Model(inputs=conv_model.input, outputs=predictions)
  full_model.summary()

  full_model.compile(loss='categorical_crossentropy',
                  optimizer= op,
                  metrics=['acc'])
  
  history = full_model.fit_generator(
    train_generator, 
    callbacks = [es, mc],
    validation_data = validation_generator,
    workers=10,
    epochs = ep,
  )

  
  end= datetime.now()
  elapsed= end-start
  print ('Time: ', elapsed)

  return full_model, history
In [52]:
model, history = ResNet50_model("adam", 5)

Model: "model_1"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_55 (InputLayer)           [(None, 224, 224, 3) 0                                            
__________________________________________________________________________________________________
conv1_pad (ZeroPadding2D)       (None, 230, 230, 3)  0           input_55[0][0]                   
__________________________________________________________________________________________________
conv1_conv (Conv2D)             (None, 112, 112, 64) 9472        conv1_pad[0][0]                  
__________________________________________________________________________________________________
conv1_bn (BatchNormalization)   (None, 112, 112, 64) 256         conv1_conv[0][0]                 
__________________________________________________________________________________________________
conv1_relu (Activation)         (None, 112, 112, 64) 0           conv1_bn[0][0]                   
__________________________________________________________________________________________________
pool1_pad (ZeroPadding2D)       (None, 114, 114, 64) 0           conv1_relu[0][0]                 
__________________________________________________________________________________________________
pool1_pool (MaxPooling2D)       (None, 56, 56, 64)   0           pool1_pad[0][0]                  
__________________________________________________________________________________________________
conv2_block1_1_conv (Conv2D)    (None, 56, 56, 64)   4160        pool1_pool[0][0]                 
__________________________________________________________________________________________________
conv2_block1_1_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block1_1_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_1_relu (Activation (None, 56, 56, 64)   0           conv2_block1_1_bn[0][0]          
__________________________________________________________________________________________________
conv2_block1_2_conv (Conv2D)    (None, 56, 56, 64)   36928       conv2_block1_1_relu[0][0]        
__________________________________________________________________________________________________
conv2_block1_2_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block1_2_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_2_relu (Activation (None, 56, 56, 64)   0           conv2_block1_2_bn[0][0]          
__________________________________________________________________________________________________
conv2_block1_0_conv (Conv2D)    (None, 56, 56, 256)  16640       pool1_pool[0][0]                 
__________________________________________________________________________________________________
conv2_block1_3_conv (Conv2D)    (None, 56, 56, 256)  16640       conv2_block1_2_relu[0][0]        
__________________________________________________________________________________________________
conv2_block1_0_bn (BatchNormali (None, 56, 56, 256)  1024        conv2_block1_0_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_3_bn (BatchNormali (None, 56, 56, 256)  1024        conv2_block1_3_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_add (Add)          (None, 56, 56, 256)  0           conv2_block1_0_bn[0][0]          
                                                                 conv2_block1_3_bn[0][0]          
__________________________________________________________________________________________________
conv2_block1_out (Activation)   (None, 56, 56, 256)  0           conv2_block1_add[0][0]           
__________________________________________________________________________________________________
conv2_block2_1_conv (Conv2D)    (None, 56, 56, 64)   16448       conv2_block1_out[0][0]           
__________________________________________________________________________________________________
conv2_block2_1_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block2_1_conv[0][0]        
__________________________________________________________________________________________________
conv2_block2_1_relu (Activation (None, 56, 56, 64)   0           conv2_block2_1_bn[0][0]          
__________________________________________________________________________________________________
conv2_block2_2_conv (Conv2D)    (None, 56, 56, 64)   36928       conv2_block2_1_relu[0][0]        
__________________________________________________________________________________________________
conv2_block2_2_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block2_2_conv[0][0]        
__________________________________________________________________________________________________
conv2_block2_2_relu (Activation (None, 56, 56, 64)   0           conv2_block2_2_bn[0][0]          
__________________________________________________________________________________________________
conv2_block2_3_conv (Conv2D)    (None, 56, 56, 256)  16640       conv2_block2_2_relu[0][0]        
__________________________________________________________________________________________________
conv2_block2_3_bn (BatchNormali (None, 56, 56, 256)  1024        conv2_block2_3_conv[0][0]        
__________________________________________________________________________________________________
conv2_block2_add (Add)          (None, 56, 56, 256)  0           conv2_block1_out[0][0]           
                                                                 conv2_block2_3_bn[0][0]          
__________________________________________________________________________________________________
conv2_block2_out (Activation)   (None, 56, 56, 256)  0           conv2_block2_add[0][0]           
__________________________________________________________________________________________________
conv2_block3_1_conv (Conv2D)    (None, 56, 56, 64)   16448       conv2_block2_out[0][0]           
__________________________________________________________________________________________________
conv2_block3_1_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block3_1_conv[0][0]        
__________________________________________________________________________________________________
conv2_block3_1_relu (Activation (None, 56, 56, 64)   0           conv2_block3_1_bn[0][0]          
__________________________________________________________________________________________________
conv2_block3_2_conv (Conv2D)    (None, 56, 56, 64)   36928       conv2_block3_1_relu[0][0]        
__________________________________________________________________________________________________
conv2_block3_2_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block3_2_conv[0][0]        
__________________________________________________________________________________________________
conv2_block3_2_relu (Activation (None, 56, 56, 64)   0           conv2_block3_2_bn[0][0]          
__________________________________________________________________________________________________
conv2_block3_3_conv (Conv2D)    (None, 56, 56, 256)  16640       conv2_block3_2_relu[0][0]        
__________________________________________________________________________________________________
conv2_block3_3_bn (BatchNormali (None, 56, 56, 256)  1024        conv2_block3_3_conv[0][0]        
__________________________________________________________________________________________________
conv2_block3_add (Add)          (None, 56, 56, 256)  0           conv2_block2_out[0][0]           
                                                                 conv2_block3_3_bn[0][0]          
__________________________________________________________________________________________________
conv2_block3_out (Activation)   (None, 56, 56, 256)  0           conv2_block3_add[0][0]           
__________________________________________________________________________________________________
conv3_block1_1_conv (Conv2D)    (None, 28, 28, 128)  32896       conv2_block3_out[0][0]           
__________________________________________________________________________________________________
conv3_block1_1_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block1_1_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_1_relu (Activation (None, 28, 28, 128)  0           conv3_block1_1_bn[0][0]          
__________________________________________________________________________________________________
conv3_block1_2_conv (Conv2D)    (None, 28, 28, 128)  147584      conv3_block1_1_relu[0][0]        
__________________________________________________________________________________________________
conv3_block1_2_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block1_2_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_2_relu (Activation (None, 28, 28, 128)  0           conv3_block1_2_bn[0][0]          
__________________________________________________________________________________________________
conv3_block1_0_conv (Conv2D)    (None, 28, 28, 512)  131584      conv2_block3_out[0][0]           
__________________________________________________________________________________________________
conv3_block1_3_conv (Conv2D)    (None, 28, 28, 512)  66048       conv3_block1_2_relu[0][0]        
__________________________________________________________________________________________________
conv3_block1_0_bn (BatchNormali (None, 28, 28, 512)  2048        conv3_block1_0_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_3_bn (BatchNormali (None, 28, 28, 512)  2048        conv3_block1_3_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_add (Add)          (None, 28, 28, 512)  0           conv3_block1_0_bn[0][0]          
                                                                 conv3_block1_3_bn[0][0]          
__________________________________________________________________________________________________
conv3_block1_out (Activation)   (None, 28, 28, 512)  0           conv3_block1_add[0][0]           
__________________________________________________________________________________________________
conv3_block2_1_conv (Conv2D)    (None, 28, 28, 128)  65664       conv3_block1_out[0][0]           
__________________________________________________________________________________________________
conv3_block2_1_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block2_1_conv[0][0]        
__________________________________________________________________________________________________
conv3_block2_1_relu (Activation (None, 28, 28, 128)  0           conv3_block2_1_bn[0][0]          
__________________________________________________________________________________________________
conv3_block2_2_conv (Conv2D)    (None, 28, 28, 128)  147584      conv3_block2_1_relu[0][0]        
__________________________________________________________________________________________________
conv3_block2_2_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block2_2_conv[0][0]        
__________________________________________________________________________________________________
conv3_block2_2_relu (Activation (None, 28, 28, 128)  0           conv3_block2_2_bn[0][0]          
__________________________________________________________________________________________________
conv3_block2_3_conv (Conv2D)    (None, 28, 28, 512)  66048       conv3_block2_2_relu[0][0]        
__________________________________________________________________________________________________
conv3_block2_3_bn (BatchNormali (None, 28, 28, 512)  2048        conv3_block2_3_conv[0][0]        
__________________________________________________________________________________________________
conv3_block2_add (Add)          (None, 28, 28, 512)  0           conv3_block1_out[0][0]           
                                                                 conv3_block2_3_bn[0][0]          
__________________________________________________________________________________________________
conv3_block2_out (Activation)   (None, 28, 28, 512)  0           conv3_block2_add[0][0]           
__________________________________________________________________________________________________
conv3_block3_1_conv (Conv2D)    (None, 28, 28, 128)  65664       conv3_block2_out[0][0]           
__________________________________________________________________________________________________
conv3_block3_1_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block3_1_conv[0][0]        
__________________________________________________________________________________________________
conv3_block3_1_relu (Activation (None, 28, 28, 128)  0           conv3_block3_1_bn[0][0]          
__________________________________________________________________________________________________
conv3_block3_2_conv (Conv2D)    (None, 28, 28, 128)  147584      conv3_block3_1_relu[0][0]        
__________________________________________________________________________________________________
conv3_block3_2_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block3_2_conv[0][0]        
__________________________________________________________________________________________________
conv3_block3_2_relu (Activation (None, 28, 28, 128)  0           conv3_block3_2_bn[0][0]          
__________________________________________________________________________________________________
conv3_block3_3_conv (Conv2D)    (None, 28, 28, 512)  66048       conv3_block3_2_relu[0][0]        
__________________________________________________________________________________________________
conv3_block3_3_bn (BatchNormali (None, 28, 28, 512)  2048        conv3_block3_3_conv[0][0]        
__________________________________________________________________________________________________
conv3_block3_add (Add)          (None, 28, 28, 512)  0           conv3_block2_out[0][0]           
                                                                 conv3_block3_3_bn[0][0]          
__________________________________________________________________________________________________
conv3_block3_out (Activation)   (None, 28, 28, 512)  0           conv3_block3_add[0][0]           
__________________________________________________________________________________________________
conv3_block4_1_conv (Conv2D)    (None, 28, 28, 128)  65664       conv3_block3_out[0][0]           
__________________________________________________________________________________________________
conv3_block4_1_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block4_1_conv[0][0]        
__________________________________________________________________________________________________
conv3_block4_1_relu (Activation (None, 28, 28, 128)  0           conv3_block4_1_bn[0][0]          
__________________________________________________________________________________________________
conv3_block4_2_conv (Conv2D)    (None, 28, 28, 128)  147584      conv3_block4_1_relu[0][0]        
__________________________________________________________________________________________________
conv3_block4_2_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block4_2_conv[0][0]        
__________________________________________________________________________________________________
conv3_block4_2_relu (Activation (None, 28, 28, 128)  0           conv3_block4_2_bn[0][0]          
__________________________________________________________________________________________________
conv3_block4_3_conv (Conv2D)    (None, 28, 28, 512)  66048       conv3_block4_2_relu[0][0]        
__________________________________________________________________________________________________
conv3_block4_3_bn (BatchNormali (None, 28, 28, 512)  2048        conv3_block4_3_conv[0][0]        
__________________________________________________________________________________________________
conv3_block4_add (Add)          (None, 28, 28, 512)  0           conv3_block3_out[0][0]           
                                                                 conv3_block4_3_bn[0][0]          
__________________________________________________________________________________________________
conv3_block4_out (Activation)   (None, 28, 28, 512)  0           conv3_block4_add[0][0]           
__________________________________________________________________________________________________
conv4_block1_1_conv (Conv2D)    (None, 14, 14, 256)  131328      conv3_block4_out[0][0]           
__________________________________________________________________________________________________
conv4_block1_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block1_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block1_1_relu (Activation (None, 14, 14, 256)  0           conv4_block1_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block1_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block1_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block1_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block1_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block1_2_relu (Activation (None, 14, 14, 256)  0           conv4_block1_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block1_0_conv (Conv2D)    (None, 14, 14, 1024) 525312      conv3_block4_out[0][0]           
__________________________________________________________________________________________________
conv4_block1_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block1_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block1_0_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block1_0_conv[0][0]        
__________________________________________________________________________________________________
conv4_block1_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block1_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block1_add (Add)          (None, 14, 14, 1024) 0           conv4_block1_0_bn[0][0]          
                                                                 conv4_block1_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block1_out (Activation)   (None, 14, 14, 1024) 0           conv4_block1_add[0][0]           
__________________________________________________________________________________________________
conv4_block2_1_conv (Conv2D)    (None, 14, 14, 256)  262400      conv4_block1_out[0][0]           
__________________________________________________________________________________________________
conv4_block2_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block2_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block2_1_relu (Activation (None, 14, 14, 256)  0           conv4_block2_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block2_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block2_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block2_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block2_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block2_2_relu (Activation (None, 14, 14, 256)  0           conv4_block2_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block2_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block2_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block2_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block2_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block2_add (Add)          (None, 14, 14, 1024) 0           conv4_block1_out[0][0]           
                                                                 conv4_block2_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block2_out (Activation)   (None, 14, 14, 1024) 0           conv4_block2_add[0][0]           
__________________________________________________________________________________________________
conv4_block3_1_conv (Conv2D)    (None, 14, 14, 256)  262400      conv4_block2_out[0][0]           
__________________________________________________________________________________________________
conv4_block3_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block3_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block3_1_relu (Activation (None, 14, 14, 256)  0           conv4_block3_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block3_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block3_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block3_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block3_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block3_2_relu (Activation (None, 14, 14, 256)  0           conv4_block3_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block3_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block3_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block3_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block3_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block3_add (Add)          (None, 14, 14, 1024) 0           conv4_block2_out[0][0]           
                                                                 conv4_block3_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block3_out (Activation)   (None, 14, 14, 1024) 0           conv4_block3_add[0][0]           
__________________________________________________________________________________________________
conv4_block4_1_conv (Conv2D)    (None, 14, 14, 256)  262400      conv4_block3_out[0][0]           
__________________________________________________________________________________________________
conv4_block4_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block4_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block4_1_relu (Activation (None, 14, 14, 256)  0           conv4_block4_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block4_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block4_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block4_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block4_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block4_2_relu (Activation (None, 14, 14, 256)  0           conv4_block4_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block4_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block4_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block4_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block4_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block4_add (Add)          (None, 14, 14, 1024) 0           conv4_block3_out[0][0]           
                                                                 conv4_block4_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block4_out (Activation)   (None, 14, 14, 1024) 0           conv4_block4_add[0][0]           
__________________________________________________________________________________________________
conv4_block5_1_conv (Conv2D)    (None, 14, 14, 256)  262400      conv4_block4_out[0][0]           
__________________________________________________________________________________________________
conv4_block5_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block5_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block5_1_relu (Activation (None, 14, 14, 256)  0           conv4_block5_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block5_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block5_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block5_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block5_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block5_2_relu (Activation (None, 14, 14, 256)  0           conv4_block5_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block5_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block5_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block5_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block5_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block5_add (Add)          (None, 14, 14, 1024) 0           conv4_block4_out[0][0]           
                                                                 conv4_block5_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block5_out (Activation)   (None, 14, 14, 1024) 0           conv4_block5_add[0][0]           
__________________________________________________________________________________________________
conv4_block6_1_conv (Conv2D)    (None, 14, 14, 256)  262400      conv4_block5_out[0][0]           
__________________________________________________________________________________________________
conv4_block6_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block6_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block6_1_relu (Activation (None, 14, 14, 256)  0           conv4_block6_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block6_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block6_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block6_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block6_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block6_2_relu (Activation (None, 14, 14, 256)  0           conv4_block6_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block6_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block6_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block6_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block6_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block6_add (Add)          (None, 14, 14, 1024) 0           conv4_block5_out[0][0]           
                                                                 conv4_block6_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block6_out (Activation)   (None, 14, 14, 1024) 0           conv4_block6_add[0][0]           
__________________________________________________________________________________________________
conv5_block1_1_conv (Conv2D)    (None, 7, 7, 512)    524800      conv4_block6_out[0][0]           
__________________________________________________________________________________________________
conv5_block1_1_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block1_1_conv[0][0]        
__________________________________________________________________________________________________
conv5_block1_1_relu (Activation (None, 7, 7, 512)    0           conv5_block1_1_bn[0][0]          
__________________________________________________________________________________________________
conv5_block1_2_conv (Conv2D)    (None, 7, 7, 512)    2359808     conv5_block1_1_relu[0][0]        
__________________________________________________________________________________________________
conv5_block1_2_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block1_2_conv[0][0]        
__________________________________________________________________________________________________
conv5_block1_2_relu (Activation (None, 7, 7, 512)    0           conv5_block1_2_bn[0][0]          
__________________________________________________________________________________________________
conv5_block1_0_conv (Conv2D)    (None, 7, 7, 2048)   2099200     conv4_block6_out[0][0]           
__________________________________________________________________________________________________
conv5_block1_3_conv (Conv2D)    (None, 7, 7, 2048)   1050624     conv5_block1_2_relu[0][0]        
__________________________________________________________________________________________________
conv5_block1_0_bn (BatchNormali (None, 7, 7, 2048)   8192        conv5_block1_0_conv[0][0]        
__________________________________________________________________________________________________
conv5_block1_3_bn (BatchNormali (None, 7, 7, 2048)   8192        conv5_block1_3_conv[0][0]        
__________________________________________________________________________________________________
conv5_block1_add (Add)          (None, 7, 7, 2048)   0           conv5_block1_0_bn[0][0]          
                                                                 conv5_block1_3_bn[0][0]          
__________________________________________________________________________________________________
conv5_block1_out (Activation)   (None, 7, 7, 2048)   0           conv5_block1_add[0][0]           
__________________________________________________________________________________________________
conv5_block2_1_conv (Conv2D)    (None, 7, 7, 512)    1049088     conv5_block1_out[0][0]           
__________________________________________________________________________________________________
conv5_block2_1_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block2_1_conv[0][0]        
__________________________________________________________________________________________________
conv5_block2_1_relu (Activation (None, 7, 7, 512)    0           conv5_block2_1_bn[0][0]          
__________________________________________________________________________________________________
conv5_block2_2_conv (Conv2D)    (None, 7, 7, 512)    2359808     conv5_block2_1_relu[0][0]        
__________________________________________________________________________________________________
conv5_block2_2_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block2_2_conv[0][0]        
__________________________________________________________________________________________________
conv5_block2_2_relu (Activation (None, 7, 7, 512)    0           conv5_block2_2_bn[0][0]          
__________________________________________________________________________________________________
conv5_block2_3_conv (Conv2D)    (None, 7, 7, 2048)   1050624     conv5_block2_2_relu[0][0]        
__________________________________________________________________________________________________
conv5_block2_3_bn (BatchNormali (None, 7, 7, 2048)   8192        conv5_block2_3_conv[0][0]        
__________________________________________________________________________________________________
conv5_block2_add (Add)          (None, 7, 7, 2048)   0           conv5_block1_out[0][0]           
                                                                 conv5_block2_3_bn[0][0]          
__________________________________________________________________________________________________
conv5_block2_out (Activation)   (None, 7, 7, 2048)   0           conv5_block2_add[0][0]           
__________________________________________________________________________________________________
conv5_block3_1_conv (Conv2D)    (None, 7, 7, 512)    1049088     conv5_block2_out[0][0]           
__________________________________________________________________________________________________
conv5_block3_1_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block3_1_conv[0][0]        
__________________________________________________________________________________________________
conv5_block3_1_relu (Activation (None, 7, 7, 512)    0           conv5_block3_1_bn[0][0]          
__________________________________________________________________________________________________
conv5_block3_2_conv (Conv2D)    (None, 7, 7, 512)    2359808     conv5_block3_1_relu[0][0]        
__________________________________________________________________________________________________
conv5_block3_2_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block3_2_conv[0][0]        
__________________________________________________________________________________________________
conv5_block3_2_relu (Activation (None, 7, 7, 512)    0           conv5_block3_2_bn[0][0]          
__________________________________________________________________________________________________
conv5_block3_3_conv (Conv2D)    (None, 7, 7, 2048)   1050624     conv5_block3_2_relu[0][0]        
__________________________________________________________________________________________________
conv5_block3_3_bn (BatchNormali (None, 7, 7, 2048)   8192        conv5_block3_3_conv[0][0]        
__________________________________________________________________________________________________
conv5_block3_add (Add)          (None, 7, 7, 2048)   0           conv5_block2_out[0][0]           
                                                                 conv5_block3_3_bn[0][0]          
__________________________________________________________________________________________________
conv5_block3_out (Activation)   (None, 7, 7, 2048)   0           conv5_block3_add[0][0]           
__________________________________________________________________________________________________
flatten_9 (Flatten)             (None, 100352)       0           conv5_block3_out[0][0]           
__________________________________________________________________________________________________
dense_184 (Dense)               (None, 100)          10035300    flatten_9[0][0]                  
__________________________________________________________________________________________________
dense_185 (Dense)               (None, 100)          10100       dense_184[0][0]                  
__________________________________________________________________________________________________
dense_186 (Dense)               (None, 100)          10100       dense_185[0][0]                  
__________________________________________________________________________________________________
dense_187 (Dense)               (None, 250)          25250       dense_186[0][0]                  
==================================================================================================
Total params: 33,668,462
Trainable params: 10,080,750
Non-trainable params: 23,587,712
__________________________________________________________________________________________________
Epoch 1/5
1101/1101 [==============================] - 106s 93ms/step - loss: 5.5202 - acc: 0.0073 - val_loss: 5.5325 - val_acc: 0.0040
Epoch 2/5
1101/1101 [==============================] - 101s 92ms/step - loss: 5.5066 - acc: 0.0085 - val_loss: 5.5341 - val_acc: 0.0040
Epoch 3/5
1101/1101 [==============================] - 100s 91ms/step - loss: 5.5054 - acc: 0.0085 - val_loss: 5.5361 - val_acc: 0.0040
Epoch 4/5
1101/1101 [==============================] - 100s 91ms/step - loss: 5.5052 - acc: 0.0085 - val_loss: 5.5375 - val_acc: 0.0040
Epoch 5/5
1101/1101 [==============================] - 100s 91ms/step - loss: 5.5050 - acc: 0.0085 - val_loss: 5.5400 - val_acc: 0.0040
Time:  0:08:31.358101
In [53]:
for layers in (model.layers)[:19]:
    print(layers)
    layers.trainable = False

<keras.engine.input_layer.InputLayer object at 0x000001B5387C86C8>
<keras.layers.convolutional.ZeroPadding2D object at 0x000001B927A80F08>
<keras.layers.convolutional.Conv2D object at 0x000001B927C130C8>
<keras.layers.normalization.batch_normalization.BatchNormalization object at 0x000001B927749BC8>
<keras.layers.core.Activation object at 0x000001B927E91588>
<keras.layers.convolutional.ZeroPadding2D object at 0x000001B92885A608>
<keras.layers.pooling.MaxPooling2D object at 0x000001B92884F908>
<keras.layers.convolutional.Conv2D object at 0x000001B928B1DF08>
<keras.layers.normalization.batch_normalization.BatchNormalization object at 0x000001B928B1D048>
<keras.layers.core.Activation object at 0x000001B928B35788>
<keras.layers.convolutional.Conv2D object at 0x000001B928B0A688>
<keras.layers.normalization.batch_normalization.BatchNormalization object at 0x000001B928B3BF08>
<keras.layers.core.Activation object at 0x000001B928B3CC88>
<keras.layers.convolutional.Conv2D object at 0x000001B927B98108>
<keras.layers.convolutional.Conv2D object at 0x000001B928B0DEC8>
<keras.layers.normalization.batch_normalization.BatchNormalization object at 0x000001B928668688>
<keras.layers.normalization.batch_normalization.BatchNormalization object at 0x000001B928B285C8>
<keras.layers.merge.Add object at 0x000001B928A56548>
<keras.layers.core.Activation object at 0x000001B928A408C8>
In [54]:
X= model.layers[-2].output
predictions = Dense(2, activation="softmax")(X)
model_final = Model(model.input, predictions)
In [55]:
model_final.compile(loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), optimizer = optimizers.SGD(lr=0.0001, momentum=0.9), metrics=["accuracy"])

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\optimizer_v2\optimizer_v2.py:356: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  "The `lr` argument is deprecated, use `learning_rate` instead.")
In [56]:
model_final.summary()

Model: "model_2"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_55 (InputLayer)           [(None, 224, 224, 3) 0                                            
__________________________________________________________________________________________________
conv1_pad (ZeroPadding2D)       (None, 230, 230, 3)  0           input_55[0][0]                   
__________________________________________________________________________________________________
conv1_conv (Conv2D)             (None, 112, 112, 64) 9472        conv1_pad[0][0]                  
__________________________________________________________________________________________________
conv1_bn (BatchNormalization)   (None, 112, 112, 64) 256         conv1_conv[0][0]                 
__________________________________________________________________________________________________
conv1_relu (Activation)         (None, 112, 112, 64) 0           conv1_bn[0][0]                   
__________________________________________________________________________________________________
pool1_pad (ZeroPadding2D)       (None, 114, 114, 64) 0           conv1_relu[0][0]                 
__________________________________________________________________________________________________
pool1_pool (MaxPooling2D)       (None, 56, 56, 64)   0           pool1_pad[0][0]                  
__________________________________________________________________________________________________
conv2_block1_1_conv (Conv2D)    (None, 56, 56, 64)   4160        pool1_pool[0][0]                 
__________________________________________________________________________________________________
conv2_block1_1_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block1_1_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_1_relu (Activation (None, 56, 56, 64)   0           conv2_block1_1_bn[0][0]          
__________________________________________________________________________________________________
conv2_block1_2_conv (Conv2D)    (None, 56, 56, 64)   36928       conv2_block1_1_relu[0][0]        
__________________________________________________________________________________________________
conv2_block1_2_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block1_2_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_2_relu (Activation (None, 56, 56, 64)   0           conv2_block1_2_bn[0][0]          
__________________________________________________________________________________________________
conv2_block1_0_conv (Conv2D)    (None, 56, 56, 256)  16640       pool1_pool[0][0]                 
__________________________________________________________________________________________________
conv2_block1_3_conv (Conv2D)    (None, 56, 56, 256)  16640       conv2_block1_2_relu[0][0]        
__________________________________________________________________________________________________
conv2_block1_0_bn (BatchNormali (None, 56, 56, 256)  1024        conv2_block1_0_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_3_bn (BatchNormali (None, 56, 56, 256)  1024        conv2_block1_3_conv[0][0]        
__________________________________________________________________________________________________
conv2_block1_add (Add)          (None, 56, 56, 256)  0           conv2_block1_0_bn[0][0]          
                                                                 conv2_block1_3_bn[0][0]          
__________________________________________________________________________________________________
conv2_block1_out (Activation)   (None, 56, 56, 256)  0           conv2_block1_add[0][0]           
__________________________________________________________________________________________________
conv2_block2_1_conv (Conv2D)    (None, 56, 56, 64)   16448       conv2_block1_out[0][0]           
__________________________________________________________________________________________________
conv2_block2_1_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block2_1_conv[0][0]        
__________________________________________________________________________________________________
conv2_block2_1_relu (Activation (None, 56, 56, 64)   0           conv2_block2_1_bn[0][0]          
__________________________________________________________________________________________________
conv2_block2_2_conv (Conv2D)    (None, 56, 56, 64)   36928       conv2_block2_1_relu[0][0]        
__________________________________________________________________________________________________
conv2_block2_2_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block2_2_conv[0][0]        
__________________________________________________________________________________________________
conv2_block2_2_relu (Activation (None, 56, 56, 64)   0           conv2_block2_2_bn[0][0]          
__________________________________________________________________________________________________
conv2_block2_3_conv (Conv2D)    (None, 56, 56, 256)  16640       conv2_block2_2_relu[0][0]        
__________________________________________________________________________________________________
conv2_block2_3_bn (BatchNormali (None, 56, 56, 256)  1024        conv2_block2_3_conv[0][0]        
__________________________________________________________________________________________________
conv2_block2_add (Add)          (None, 56, 56, 256)  0           conv2_block1_out[0][0]           
                                                                 conv2_block2_3_bn[0][0]          
__________________________________________________________________________________________________
conv2_block2_out (Activation)   (None, 56, 56, 256)  0           conv2_block2_add[0][0]           
__________________________________________________________________________________________________
conv2_block3_1_conv (Conv2D)    (None, 56, 56, 64)   16448       conv2_block2_out[0][0]           
__________________________________________________________________________________________________
conv2_block3_1_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block3_1_conv[0][0]        
__________________________________________________________________________________________________
conv2_block3_1_relu (Activation (None, 56, 56, 64)   0           conv2_block3_1_bn[0][0]          
__________________________________________________________________________________________________
conv2_block3_2_conv (Conv2D)    (None, 56, 56, 64)   36928       conv2_block3_1_relu[0][0]        
__________________________________________________________________________________________________
conv2_block3_2_bn (BatchNormali (None, 56, 56, 64)   256         conv2_block3_2_conv[0][0]        
__________________________________________________________________________________________________
conv2_block3_2_relu (Activation (None, 56, 56, 64)   0           conv2_block3_2_bn[0][0]          
__________________________________________________________________________________________________
conv2_block3_3_conv (Conv2D)    (None, 56, 56, 256)  16640       conv2_block3_2_relu[0][0]        
__________________________________________________________________________________________________
conv2_block3_3_bn (BatchNormali (None, 56, 56, 256)  1024        conv2_block3_3_conv[0][0]        
__________________________________________________________________________________________________
conv2_block3_add (Add)          (None, 56, 56, 256)  0           conv2_block2_out[0][0]           
                                                                 conv2_block3_3_bn[0][0]          
__________________________________________________________________________________________________
conv2_block3_out (Activation)   (None, 56, 56, 256)  0           conv2_block3_add[0][0]           
__________________________________________________________________________________________________
conv3_block1_1_conv (Conv2D)    (None, 28, 28, 128)  32896       conv2_block3_out[0][0]           
__________________________________________________________________________________________________
conv3_block1_1_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block1_1_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_1_relu (Activation (None, 28, 28, 128)  0           conv3_block1_1_bn[0][0]          
__________________________________________________________________________________________________
conv3_block1_2_conv (Conv2D)    (None, 28, 28, 128)  147584      conv3_block1_1_relu[0][0]        
__________________________________________________________________________________________________
conv3_block1_2_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block1_2_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_2_relu (Activation (None, 28, 28, 128)  0           conv3_block1_2_bn[0][0]          
__________________________________________________________________________________________________
conv3_block1_0_conv (Conv2D)    (None, 28, 28, 512)  131584      conv2_block3_out[0][0]           
__________________________________________________________________________________________________
conv3_block1_3_conv (Conv2D)    (None, 28, 28, 512)  66048       conv3_block1_2_relu[0][0]        
__________________________________________________________________________________________________
conv3_block1_0_bn (BatchNormali (None, 28, 28, 512)  2048        conv3_block1_0_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_3_bn (BatchNormali (None, 28, 28, 512)  2048        conv3_block1_3_conv[0][0]        
__________________________________________________________________________________________________
conv3_block1_add (Add)          (None, 28, 28, 512)  0           conv3_block1_0_bn[0][0]          
                                                                 conv3_block1_3_bn[0][0]          
__________________________________________________________________________________________________
conv3_block1_out (Activation)   (None, 28, 28, 512)  0           conv3_block1_add[0][0]           
__________________________________________________________________________________________________
conv3_block2_1_conv (Conv2D)    (None, 28, 28, 128)  65664       conv3_block1_out[0][0]           
__________________________________________________________________________________________________
conv3_block2_1_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block2_1_conv[0][0]        
__________________________________________________________________________________________________
conv3_block2_1_relu (Activation (None, 28, 28, 128)  0           conv3_block2_1_bn[0][0]          
__________________________________________________________________________________________________
conv3_block2_2_conv (Conv2D)    (None, 28, 28, 128)  147584      conv3_block2_1_relu[0][0]        
__________________________________________________________________________________________________
conv3_block2_2_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block2_2_conv[0][0]        
__________________________________________________________________________________________________
conv3_block2_2_relu (Activation (None, 28, 28, 128)  0           conv3_block2_2_bn[0][0]          
__________________________________________________________________________________________________
conv3_block2_3_conv (Conv2D)    (None, 28, 28, 512)  66048       conv3_block2_2_relu[0][0]        
__________________________________________________________________________________________________
conv3_block2_3_bn (BatchNormali (None, 28, 28, 512)  2048        conv3_block2_3_conv[0][0]        
__________________________________________________________________________________________________
conv3_block2_add (Add)          (None, 28, 28, 512)  0           conv3_block1_out[0][0]           
                                                                 conv3_block2_3_bn[0][0]          
__________________________________________________________________________________________________
conv3_block2_out (Activation)   (None, 28, 28, 512)  0           conv3_block2_add[0][0]           
__________________________________________________________________________________________________
conv3_block3_1_conv (Conv2D)    (None, 28, 28, 128)  65664       conv3_block2_out[0][0]           
__________________________________________________________________________________________________
conv3_block3_1_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block3_1_conv[0][0]        
__________________________________________________________________________________________________
conv3_block3_1_relu (Activation (None, 28, 28, 128)  0           conv3_block3_1_bn[0][0]          
__________________________________________________________________________________________________
conv3_block3_2_conv (Conv2D)    (None, 28, 28, 128)  147584      conv3_block3_1_relu[0][0]        
__________________________________________________________________________________________________
conv3_block3_2_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block3_2_conv[0][0]        
__________________________________________________________________________________________________
conv3_block3_2_relu (Activation (None, 28, 28, 128)  0           conv3_block3_2_bn[0][0]          
__________________________________________________________________________________________________
conv3_block3_3_conv (Conv2D)    (None, 28, 28, 512)  66048       conv3_block3_2_relu[0][0]        
__________________________________________________________________________________________________
conv3_block3_3_bn (BatchNormali (None, 28, 28, 512)  2048        conv3_block3_3_conv[0][0]        
__________________________________________________________________________________________________
conv3_block3_add (Add)          (None, 28, 28, 512)  0           conv3_block2_out[0][0]           
                                                                 conv3_block3_3_bn[0][0]          
__________________________________________________________________________________________________
conv3_block3_out (Activation)   (None, 28, 28, 512)  0           conv3_block3_add[0][0]           
__________________________________________________________________________________________________
conv3_block4_1_conv (Conv2D)    (None, 28, 28, 128)  65664       conv3_block3_out[0][0]           
__________________________________________________________________________________________________
conv3_block4_1_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block4_1_conv[0][0]        
__________________________________________________________________________________________________
conv3_block4_1_relu (Activation (None, 28, 28, 128)  0           conv3_block4_1_bn[0][0]          
__________________________________________________________________________________________________
conv3_block4_2_conv (Conv2D)    (None, 28, 28, 128)  147584      conv3_block4_1_relu[0][0]        
__________________________________________________________________________________________________
conv3_block4_2_bn (BatchNormali (None, 28, 28, 128)  512         conv3_block4_2_conv[0][0]        
__________________________________________________________________________________________________
conv3_block4_2_relu (Activation (None, 28, 28, 128)  0           conv3_block4_2_bn[0][0]          
__________________________________________________________________________________________________
conv3_block4_3_conv (Conv2D)    (None, 28, 28, 512)  66048       conv3_block4_2_relu[0][0]        
__________________________________________________________________________________________________
conv3_block4_3_bn (BatchNormali (None, 28, 28, 512)  2048        conv3_block4_3_conv[0][0]        
__________________________________________________________________________________________________
conv3_block4_add (Add)          (None, 28, 28, 512)  0           conv3_block3_out[0][0]           
                                                                 conv3_block4_3_bn[0][0]          
__________________________________________________________________________________________________
conv3_block4_out (Activation)   (None, 28, 28, 512)  0           conv3_block4_add[0][0]           
__________________________________________________________________________________________________
conv4_block1_1_conv (Conv2D)    (None, 14, 14, 256)  131328      conv3_block4_out[0][0]           
__________________________________________________________________________________________________
conv4_block1_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block1_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block1_1_relu (Activation (None, 14, 14, 256)  0           conv4_block1_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block1_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block1_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block1_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block1_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block1_2_relu (Activation (None, 14, 14, 256)  0           conv4_block1_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block1_0_conv (Conv2D)    (None, 14, 14, 1024) 525312      conv3_block4_out[0][0]           
__________________________________________________________________________________________________
conv4_block1_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block1_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block1_0_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block1_0_conv[0][0]        
__________________________________________________________________________________________________
conv4_block1_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block1_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block1_add (Add)          (None, 14, 14, 1024) 0           conv4_block1_0_bn[0][0]          
                                                                 conv4_block1_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block1_out (Activation)   (None, 14, 14, 1024) 0           conv4_block1_add[0][0]           
__________________________________________________________________________________________________
conv4_block2_1_conv (Conv2D)    (None, 14, 14, 256)  262400      conv4_block1_out[0][0]           
__________________________________________________________________________________________________
conv4_block2_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block2_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block2_1_relu (Activation (None, 14, 14, 256)  0           conv4_block2_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block2_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block2_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block2_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block2_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block2_2_relu (Activation (None, 14, 14, 256)  0           conv4_block2_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block2_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block2_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block2_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block2_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block2_add (Add)          (None, 14, 14, 1024) 0           conv4_block1_out[0][0]           
                                                                 conv4_block2_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block2_out (Activation)   (None, 14, 14, 1024) 0           conv4_block2_add[0][0]           
__________________________________________________________________________________________________
conv4_block3_1_conv (Conv2D)    (None, 14, 14, 256)  262400      conv4_block2_out[0][0]           
__________________________________________________________________________________________________
conv4_block3_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block3_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block3_1_relu (Activation (None, 14, 14, 256)  0           conv4_block3_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block3_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block3_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block3_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block3_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block3_2_relu (Activation (None, 14, 14, 256)  0           conv4_block3_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block3_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block3_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block3_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block3_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block3_add (Add)          (None, 14, 14, 1024) 0           conv4_block2_out[0][0]           
                                                                 conv4_block3_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block3_out (Activation)   (None, 14, 14, 1024) 0           conv4_block3_add[0][0]           
__________________________________________________________________________________________________
conv4_block4_1_conv (Conv2D)    (None, 14, 14, 256)  262400      conv4_block3_out[0][0]           
__________________________________________________________________________________________________
conv4_block4_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block4_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block4_1_relu (Activation (None, 14, 14, 256)  0           conv4_block4_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block4_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block4_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block4_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block4_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block4_2_relu (Activation (None, 14, 14, 256)  0           conv4_block4_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block4_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block4_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block4_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block4_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block4_add (Add)          (None, 14, 14, 1024) 0           conv4_block3_out[0][0]           
                                                                 conv4_block4_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block4_out (Activation)   (None, 14, 14, 1024) 0           conv4_block4_add[0][0]           
__________________________________________________________________________________________________
conv4_block5_1_conv (Conv2D)    (None, 14, 14, 256)  262400      conv4_block4_out[0][0]           
__________________________________________________________________________________________________
conv4_block5_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block5_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block5_1_relu (Activation (None, 14, 14, 256)  0           conv4_block5_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block5_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block5_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block5_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block5_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block5_2_relu (Activation (None, 14, 14, 256)  0           conv4_block5_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block5_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block5_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block5_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block5_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block5_add (Add)          (None, 14, 14, 1024) 0           conv4_block4_out[0][0]           
                                                                 conv4_block5_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block5_out (Activation)   (None, 14, 14, 1024) 0           conv4_block5_add[0][0]           
__________________________________________________________________________________________________
conv4_block6_1_conv (Conv2D)    (None, 14, 14, 256)  262400      conv4_block5_out[0][0]           
__________________________________________________________________________________________________
conv4_block6_1_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block6_1_conv[0][0]        
__________________________________________________________________________________________________
conv4_block6_1_relu (Activation (None, 14, 14, 256)  0           conv4_block6_1_bn[0][0]          
__________________________________________________________________________________________________
conv4_block6_2_conv (Conv2D)    (None, 14, 14, 256)  590080      conv4_block6_1_relu[0][0]        
__________________________________________________________________________________________________
conv4_block6_2_bn (BatchNormali (None, 14, 14, 256)  1024        conv4_block6_2_conv[0][0]        
__________________________________________________________________________________________________
conv4_block6_2_relu (Activation (None, 14, 14, 256)  0           conv4_block6_2_bn[0][0]          
__________________________________________________________________________________________________
conv4_block6_3_conv (Conv2D)    (None, 14, 14, 1024) 263168      conv4_block6_2_relu[0][0]        
__________________________________________________________________________________________________
conv4_block6_3_bn (BatchNormali (None, 14, 14, 1024) 4096        conv4_block6_3_conv[0][0]        
__________________________________________________________________________________________________
conv4_block6_add (Add)          (None, 14, 14, 1024) 0           conv4_block5_out[0][0]           
                                                                 conv4_block6_3_bn[0][0]          
__________________________________________________________________________________________________
conv4_block6_out (Activation)   (None, 14, 14, 1024) 0           conv4_block6_add[0][0]           
__________________________________________________________________________________________________
conv5_block1_1_conv (Conv2D)    (None, 7, 7, 512)    524800      conv4_block6_out[0][0]           
__________________________________________________________________________________________________
conv5_block1_1_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block1_1_conv[0][0]        
__________________________________________________________________________________________________
conv5_block1_1_relu (Activation (None, 7, 7, 512)    0           conv5_block1_1_bn[0][0]          
__________________________________________________________________________________________________
conv5_block1_2_conv (Conv2D)    (None, 7, 7, 512)    2359808     conv5_block1_1_relu[0][0]        
__________________________________________________________________________________________________
conv5_block1_2_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block1_2_conv[0][0]        
__________________________________________________________________________________________________
conv5_block1_2_relu (Activation (None, 7, 7, 512)    0           conv5_block1_2_bn[0][0]          
__________________________________________________________________________________________________
conv5_block1_0_conv (Conv2D)    (None, 7, 7, 2048)   2099200     conv4_block6_out[0][0]           
__________________________________________________________________________________________________
conv5_block1_3_conv (Conv2D)    (None, 7, 7, 2048)   1050624     conv5_block1_2_relu[0][0]        
__________________________________________________________________________________________________
conv5_block1_0_bn (BatchNormali (None, 7, 7, 2048)   8192        conv5_block1_0_conv[0][0]        
__________________________________________________________________________________________________
conv5_block1_3_bn (BatchNormali (None, 7, 7, 2048)   8192        conv5_block1_3_conv[0][0]        
__________________________________________________________________________________________________
conv5_block1_add (Add)          (None, 7, 7, 2048)   0           conv5_block1_0_bn[0][0]          
                                                                 conv5_block1_3_bn[0][0]          
__________________________________________________________________________________________________
conv5_block1_out (Activation)   (None, 7, 7, 2048)   0           conv5_block1_add[0][0]           
__________________________________________________________________________________________________
conv5_block2_1_conv (Conv2D)    (None, 7, 7, 512)    1049088     conv5_block1_out[0][0]           
__________________________________________________________________________________________________
conv5_block2_1_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block2_1_conv[0][0]        
__________________________________________________________________________________________________
conv5_block2_1_relu (Activation (None, 7, 7, 512)    0           conv5_block2_1_bn[0][0]          
__________________________________________________________________________________________________
conv5_block2_2_conv (Conv2D)    (None, 7, 7, 512)    2359808     conv5_block2_1_relu[0][0]        
__________________________________________________________________________________________________
conv5_block2_2_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block2_2_conv[0][0]        
__________________________________________________________________________________________________
conv5_block2_2_relu (Activation (None, 7, 7, 512)    0           conv5_block2_2_bn[0][0]          
__________________________________________________________________________________________________
conv5_block2_3_conv (Conv2D)    (None, 7, 7, 2048)   1050624     conv5_block2_2_relu[0][0]        
__________________________________________________________________________________________________
conv5_block2_3_bn (BatchNormali (None, 7, 7, 2048)   8192        conv5_block2_3_conv[0][0]        
__________________________________________________________________________________________________
conv5_block2_add (Add)          (None, 7, 7, 2048)   0           conv5_block1_out[0][0]           
                                                                 conv5_block2_3_bn[0][0]          
__________________________________________________________________________________________________
conv5_block2_out (Activation)   (None, 7, 7, 2048)   0           conv5_block2_add[0][0]           
__________________________________________________________________________________________________
conv5_block3_1_conv (Conv2D)    (None, 7, 7, 512)    1049088     conv5_block2_out[0][0]           
__________________________________________________________________________________________________
conv5_block3_1_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block3_1_conv[0][0]        
__________________________________________________________________________________________________
conv5_block3_1_relu (Activation (None, 7, 7, 512)    0           conv5_block3_1_bn[0][0]          
__________________________________________________________________________________________________
conv5_block3_2_conv (Conv2D)    (None, 7, 7, 512)    2359808     conv5_block3_1_relu[0][0]        
__________________________________________________________________________________________________
conv5_block3_2_bn (BatchNormali (None, 7, 7, 512)    2048        conv5_block3_2_conv[0][0]        
__________________________________________________________________________________________________
conv5_block3_2_relu (Activation (None, 7, 7, 512)    0           conv5_block3_2_bn[0][0]          
__________________________________________________________________________________________________
conv5_block3_3_conv (Conv2D)    (None, 7, 7, 2048)   1050624     conv5_block3_2_relu[0][0]        
__________________________________________________________________________________________________
conv5_block3_3_bn (BatchNormali (None, 7, 7, 2048)   8192        conv5_block3_3_conv[0][0]        
__________________________________________________________________________________________________
conv5_block3_add (Add)          (None, 7, 7, 2048)   0           conv5_block2_out[0][0]           
                                                                 conv5_block3_3_bn[0][0]          
__________________________________________________________________________________________________
conv5_block3_out (Activation)   (None, 7, 7, 2048)   0           conv5_block3_add[0][0]           
__________________________________________________________________________________________________
flatten_9 (Flatten)             (None, 100352)       0           conv5_block3_out[0][0]           
__________________________________________________________________________________________________
dense_184 (Dense)               (None, 100)          10035300    flatten_9[0][0]                  
__________________________________________________________________________________________________
dense_185 (Dense)               (None, 100)          10100       dense_184[0][0]                  
__________________________________________________________________________________________________
dense_186 (Dense)               (None, 100)          10100       dense_185[0][0]                  
__________________________________________________________________________________________________
dense_188 (Dense)               (None, 2)            202         dense_186[0][0]                  
==================================================================================================
Total params: 33,643,414
Trainable params: 10,055,702
Non-trainable params: 23,587,712
__________________________________________________________________________________________________

ResNet101V2¶

In [95]:
import tensorflow as tf
from tensorflow.keras.layers import Dense, Dropout, Flatten, BatchNormalization, Activation
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint
from tensorflow.keras.applications import ResNet101V2

def ResNet101V2_model(bs, activ, op, lr_value, ep):
    train_gen, validation_gen, test_gen = generate_datasets(bs, train_datagen)

    es = EarlyStopping(monitor='val_loss', patience=5)
    mc = ModelCheckpoint('best_model.h5', monitor='val_loss', mode='min', save_best_only=True)

    convlayer = ResNet101V2(input_shape=(224, 224, 3), weights='imagenet', include_top=False)
    for layer in convlayer.layers:
        layer.trainable = False

    model = tf.keras.models.Sequential()
    model.add(convlayer)
    model.add(Dropout(0.5))
    model.add(Flatten())
    model.add(BatchNormalization())
    model.add(Dense(2048, kernel_initializer='he_uniform'))
    model.add(BatchNormalization())
    model.add(Activation(activ))  # Using Activation layer here
    model.add(Dropout(0.5))
    model.add(Dense(1024, kernel_initializer='he_uniform'))
    model.add(BatchNormalization())
    model.add(Activation(activ))  # Using Activation layer here
    model.add(Dropout(0.5))
    model.add(Dense(250, activation='softmax'))  # Corrected the activation argument

    if op == "adam":
        opt = tf.keras.optimizers.Adam(lr=lr_value)
    elif op == 'sgd':
        opt = tf.keras.optimizers.SGD(lr=lr_value)
    elif op == 'adagrad':
        opt = tf.keras.optimizers.Adagrad(lr=lr_value)
    elif op == 'adadelta':
        opt = tf.keras.optimizers.Adadelta(lr=lr_value)
    elif op == 'rmsprop':
        opt = tf.keras.optimizers.RMSprop(lr=lr_value)

    model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer=opt)

    history = model.fit(train_gen, callbacks=[es, mc], validation_data=validation_gen, epochs=ep)

    return model, history
In [64]:
opt=tf.keras.optimizers.Adam(lr=0.001)
model.compile(loss='categorical_crossentropy',metrics=['accuracy'],optimizer=opt)
In [66]:
history=model.fit(train_generator, validation_data = validation_generator,epochs = 3)

Epoch 1/3
1101/1101 [==============================] - 329s 299ms/step - loss: 5.5047 - accuracy: 0.0085 - val_loss: 5.5385 - val_accuracy: 0.0040
Epoch 2/3
1101/1101 [==============================] - 345s 314ms/step - loss: 5.5045 - accuracy: 0.0085 - val_loss: 5.5356 - val_accuracy: 0.0040
Epoch 3/3
1101/1101 [==============================] - 352s 320ms/step - loss: 5.5044 - accuracy: 0.0085 - val_loss: 5.5395 - val_accuracy: 0.0040
In [68]:
opt=tf.keras.optimizers.RMSprop(lr=0.0001)
model.compile(loss='categorical_crossentropy',metrics=['accuracy'],optimizer=opt)
history_1=model.fit(train_generator,validation_data=validation_generator,
         epochs=1)

1101/1101 [==============================] - 345s 311ms/step - loss: 5.5026 - accuracy: 0.0085 - val_loss: 5.5396 - val_accuracy: 0.0040
In [96]:
model, history = ResNet101V2_model(8, 'tanh', 'adagrad', 0.01, 3)
acc = fitness_evaluation(history)
model.save("best_model.h5")

Found 35215 images belonging to 250 classes.
Found 1250 images belonging to 250 classes.
Found 1250 images belonging to 250 classes.

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\optimizer_v2\optimizer_v2.py:356: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  "The `lr` argument is deprecated, use `learning_rate` instead.")

Epoch 1/3

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_3084\128759963.py in <module>
----> 1 model, history = ResNet101V2_model(8, 'tanh', 'adagrad', 0.01, 3)
      2 acc = fitness_evaluation(history)
      3 model.save("best_model.h5")

~\AppData\Local\Temp\ipykernel_3084\1768978274.py in ResNet101V2_model(bs, activ, op, lr_value, ep)
     42     model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer=opt)
     43 
---> 44     history = model.fit(train_gen, callbacks=[es, mc], validation_data=validation_gen, epochs=ep)
     45 
     46     return model, history

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1182                 _r=1):
   1183               callbacks.on_train_batch_begin(step)
-> 1184               tmp_logs = self.train_function(iterator)
   1185               if data_handler.should_sync:
   1186                 context.async_wait()

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    883 
    884       with OptionalXlaContext(self._jit_compile):
--> 885         result = self._call(*args, **kwds)
    886 
    887       new_tracing_count = self.experimental_get_tracing_count()

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    931       # This is the first call of __call__, so we have to initialize.
    932       initializers = []
--> 933       self._initialize(args, kwds, add_initializers_to=initializers)
    934     finally:
    935       # At this point we know that the initialization is complete (or less

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
    758     self._concrete_stateful_fn = (
    759         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
--> 760             *args, **kwds))
    761 
    762     def invalid_creator_scope(*unused_args, **unused_kwds):

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   3064       args, kwargs = None, None
   3065     with self._lock:
-> 3066       graph_function, _ = self._maybe_define_function(args, kwargs)
   3067     return graph_function
   3068 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
   3461 
   3462           self._function_cache.missed.add(call_context_key)
-> 3463           graph_function = self._create_graph_function(args, kwargs)
   3464           self._function_cache.primary[cache_key] = graph_function
   3465 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3306             arg_names=arg_names,
   3307             override_flat_arg_shapes=override_flat_arg_shapes,
-> 3308             capture_by_value=self._capture_by_value),
   3309         self._function_attributes,
   3310         function_spec=self.function_spec,

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes, acd_record_initial_resource_uses)
   1005         _, original_func = tf_decorator.unwrap(python_func)
   1006 
-> 1007       func_outputs = python_func(*func_args, **func_kwargs)
   1008 
   1009       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
    666         # the function a weak reference to itself to avoid a reference cycle.
    667         with OptionalXlaContext(compile_with_xla):
--> 668           out = weak_wrapped_fn().__wrapped__(*args, **kwds)
    669         return out
    670 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
    992           except Exception as e:  # pylint:disable=broad-except
    993             if hasattr(e, "ag_error_metadata"):
--> 994               raise e.ag_error_metadata.to_exception(e)
    995             else:
    996               raise

ValueError: in user code:

    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:853 train_function  *
        return step_function(self, iterator)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:842 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1286 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2849 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3632 _call_for_each_replica
        return fn(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:835 run_step  **
        outputs = model.train_step(data)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:789 train_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\compile_utils.py:201 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:141 __call__
        losses = call_fn(y_true, y_pred)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:245 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\util\dispatch.py:206 wrapper
        return target(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:1666 categorical_crossentropy
        y_true, y_pred, from_logits=from_logits, axis=axis)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\util\dispatch.py:206 wrapper
        return target(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\backend.py:4839 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\tensor_shape.py:1161 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, 1) and (None, 250) are incompatible
In [72]:
acc = fitness_evaluation(history)
model.save("best_model.h5")

ACC  0.008519097231328487
LOSS  5.504709243774414

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\utils\generic_utils.py:497: CustomMaskWarning: Custom mask layers require a config and must override get_config. When loading, the custom mask layer must be passed to the custom_objects argument.
  category=CustomMaskWarning)

Evaluate the performance of the model¶

Let's now evaluate the performance of the final selected model, with the test dataset.

In [73]:
lr = 0.1
bs =  16
activ = 'tanh'
op = 'adadelta'
ep = 5

model, history = ResNet101V2_model(bs, activ, op, lr, ep)

Found 35215 images belonging to 250 classes.
Found 1250 images belonging to 250 classes.
Found 1250 images belonging to 250 classes.
Model: "sequential_63"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
resnet101v2 (Functional)     (None, 7, 7, 2048)        42626560  
_________________________________________________________________
dropout_9 (Dropout)          (None, 7, 7, 2048)        0         
_________________________________________________________________
flatten_13 (Flatten)         (None, 100352)            0         
_________________________________________________________________
batch_normalization_17 (Batc (None, 100352)            401408    
_________________________________________________________________
dense_198 (Dense)            (None, 2048)              205522944 
_________________________________________________________________
batch_normalization_18 (Batc (None, 2048)              8192      
_________________________________________________________________
activation_6 (Activation)    (None, 2048)              0         
_________________________________________________________________
dropout_10 (Dropout)         (None, 2048)              0         
_________________________________________________________________
dense_199 (Dense)            (None, 1024)              2098176   
_________________________________________________________________
batch_normalization_19 (Batc (None, 1024)              4096      
_________________________________________________________________
activation_7 (Activation)    (None, 1024)              0         
_________________________________________________________________
dropout_11 (Dropout)         (None, 1024)              0         
_________________________________________________________________
dense_200 (Dense)            (None, 250)               256250    
=================================================================
Total params: 250,917,626
Trainable params: 208,084,218
Non-trainable params: 42,833,408
_________________________________________________________________
None
Epoch 1/5

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_3084\3610624396.py in <module>
      5 ep = 5
      6 
----> 7 model, history = ResNet101V2_model(bs, activ, op, lr, ep)

~\AppData\Local\Temp\ipykernel_3084\1976849179.py in ResNet101V2_model(bs, activ, op, lr_value, ep)
     46 
     47   history = model.fit(train_gen, callbacks = [es, mc], validation_data = validation_gen,
---> 48          epochs = ep)
     49 
     50   return model, history

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1182                 _r=1):
   1183               callbacks.on_train_batch_begin(step)
-> 1184               tmp_logs = self.train_function(iterator)
   1185               if data_handler.should_sync:
   1186                 context.async_wait()

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    883 
    884       with OptionalXlaContext(self._jit_compile):
--> 885         result = self._call(*args, **kwds)
    886 
    887       new_tracing_count = self.experimental_get_tracing_count()

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    931       # This is the first call of __call__, so we have to initialize.
    932       initializers = []
--> 933       self._initialize(args, kwds, add_initializers_to=initializers)
    934     finally:
    935       # At this point we know that the initialization is complete (or less

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
    758     self._concrete_stateful_fn = (
    759         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
--> 760             *args, **kwds))
    761 
    762     def invalid_creator_scope(*unused_args, **unused_kwds):

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   3064       args, kwargs = None, None
   3065     with self._lock:
-> 3066       graph_function, _ = self._maybe_define_function(args, kwargs)
   3067     return graph_function
   3068 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
   3461 
   3462           self._function_cache.missed.add(call_context_key)
-> 3463           graph_function = self._create_graph_function(args, kwargs)
   3464           self._function_cache.primary[cache_key] = graph_function
   3465 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3306             arg_names=arg_names,
   3307             override_flat_arg_shapes=override_flat_arg_shapes,
-> 3308             capture_by_value=self._capture_by_value),
   3309         self._function_attributes,
   3310         function_spec=self.function_spec,

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes, acd_record_initial_resource_uses)
   1005         _, original_func = tf_decorator.unwrap(python_func)
   1006 
-> 1007       func_outputs = python_func(*func_args, **func_kwargs)
   1008 
   1009       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
    666         # the function a weak reference to itself to avoid a reference cycle.
    667         with OptionalXlaContext(compile_with_xla):
--> 668           out = weak_wrapped_fn().__wrapped__(*args, **kwds)
    669         return out
    670 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
    992           except Exception as e:  # pylint:disable=broad-except
    993             if hasattr(e, "ag_error_metadata"):
--> 994               raise e.ag_error_metadata.to_exception(e)
    995             else:
    996               raise

ValueError: in user code:

    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:853 train_function  *
        return step_function(self, iterator)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:842 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1286 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2849 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3632 _call_for_each_replica
        return fn(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:835 run_step  **
        outputs = model.train_step(data)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:789 train_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\compile_utils.py:201 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:141 __call__
        losses = call_fn(y_true, y_pred)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:245 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\util\dispatch.py:206 wrapper
        return target(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:1666 categorical_crossentropy
        y_true, y_pred, from_logits=from_logits, axis=axis)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\util\dispatch.py:206 wrapper
        return target(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\backend.py:4839 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\tensor_shape.py:1161 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, 1) and (None, 250) are incompatible
In [74]:
fit = fitness_evaluation(history)
plot_metrics(history)
model.save('best_model.h5')

ACC  0.008519097231328487
LOSS  5.504709243774414
In [75]:
final_model = load_model('best_model.h5')
In [76]:
results = final_model.evaluate(test_generator)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_3084\3312936406.py in <module>
----> 1 results = final_model.evaluate(test_generator)

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py in evaluate(self, x, y, batch_size, verbose, sample_weight, steps, callbacks, max_queue_size, workers, use_multiprocessing, return_dict, **kwargs)
   1499             with tf.profiler.experimental.Trace('test', step_num=step, _r=1):
   1500               callbacks.on_test_batch_begin(step)
-> 1501               tmp_logs = self.test_function(iterator)
   1502               if data_handler.should_sync:
   1503                 context.async_wait()

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    883 
    884       with OptionalXlaContext(self._jit_compile):
--> 885         result = self._call(*args, **kwds)
    886 
    887       new_tracing_count = self.experimental_get_tracing_count()

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    931       # This is the first call of __call__, so we have to initialize.
    932       initializers = []
--> 933       self._initialize(args, kwds, add_initializers_to=initializers)
    934     finally:
    935       # At this point we know that the initialization is complete (or less

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
    758     self._concrete_stateful_fn = (
    759         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
--> 760             *args, **kwds))
    761 
    762     def invalid_creator_scope(*unused_args, **unused_kwds):

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   3064       args, kwargs = None, None
   3065     with self._lock:
-> 3066       graph_function, _ = self._maybe_define_function(args, kwargs)
   3067     return graph_function
   3068 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
   3461 
   3462           self._function_cache.missed.add(call_context_key)
-> 3463           graph_function = self._create_graph_function(args, kwargs)
   3464           self._function_cache.primary[cache_key] = graph_function
   3465 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3306             arg_names=arg_names,
   3307             override_flat_arg_shapes=override_flat_arg_shapes,
-> 3308             capture_by_value=self._capture_by_value),
   3309         self._function_attributes,
   3310         function_spec=self.function_spec,

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes, acd_record_initial_resource_uses)
   1005         _, original_func = tf_decorator.unwrap(python_func)
   1006 
-> 1007       func_outputs = python_func(*func_args, **func_kwargs)
   1008 
   1009       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
    666         # the function a weak reference to itself to avoid a reference cycle.
    667         with OptionalXlaContext(compile_with_xla):
--> 668           out = weak_wrapped_fn().__wrapped__(*args, **kwds)
    669         return out
    670 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
    992           except Exception as e:  # pylint:disable=broad-except
    993             if hasattr(e, "ag_error_metadata"):
--> 994               raise e.ag_error_metadata.to_exception(e)
    995             else:
    996               raise

ValueError: in user code:

    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:1330 test_function  *
        return step_function(self, iterator)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:1320 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1286 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2849 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3632 _call_for_each_replica
        return fn(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:1313 run_step  **
        outputs = model.test_step(data)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:1270 test_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\compile_utils.py:201 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:141 __call__
        losses = call_fn(y_true, y_pred)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:245 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\util\dispatch.py:206 wrapper
        return target(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:1666 categorical_crossentropy
        y_true, y_pred, from_logits=from_logits, axis=axis)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\util\dispatch.py:206 wrapper
        return target(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\backend.py:4839 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\tensor_shape.py:1161 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, 1) and (None, 250) are incompatible
In [ ]:
#print(results)
print(test_generator.classes)

[  0   0   0 ... 249 249 249]

Image class predictions¶

Let's now try to make some predictions from the images in the test dataset and then analyze the data against those predictions.

In [77]:
predictions = final_model.predict(test_generator, batch_size = 16)
In [78]:
predicted_classes = np.argmax(predictions, axis = 1)
In [79]:
true_classes = test_generator.classes
class_labels = list(test_generator.class_indices.keys())
In [80]:
print(true_classes)
print(predicted_classes)

[  0   0   0 ... 249 249 249]
[210 210 210 ... 210 210 210]
In [81]:
y_pred_gen = np.array([np.argmax(x) for x in predicted_classes])
In [82]:
y_pred_gen = y_pred_gen[:,np.newaxis]
In [83]:
x_train = train_generator.classes
y_train = test_generator.labels
In [84]:
Y_train_argmax = np.array([np.argmax(x) for x in y_train]).reshape(-1)
In [85]:
from sklearn.metrics import confusion_matrix
cm_gen = confusion_matrix(true_classes, predicted_classes)
In [86]:
print(cm_gen)

[[0 0 0 ... 0 0 0]
 [0 0 0 ... 0 0 0]
 [0 0 0 ... 0 0 0]
 ...
 [0 0 0 ... 0 0 0]
 [0 0 0 ... 0 0 0]
 [0 0 0 ... 0 0 0]]
In [87]:
import seaborn as sns
In [88]:
plt.figure(figsize = (50, 50))
sns.heatmap(cm_gen, annot = True)
plt.xlabel('Predicted Class',fontweight = 'bold')
plt.ylabel('Actual Class',fontweight = 'bold')
plt.title('Heat Map for Genetic CNN Architecture')
Out[88]:
Text(0.5, 1.0, 'Heat Map for Genetic CNN Architecture')
In [89]:
print(history)

<keras.callbacks.History object at 0x000001B860634DC8>
In [90]:
class_pred_acc = []
for i in range(250):
    class_pred_acc.append(int((cm_gen[i][i]/10) * 100))
In [91]:
plt.figure(figsize=(30, 5))
sns.barplot(x= list(range(250)), y = class_pred_acc)
plt.ylabel('Classification Accuracy %')
plt.xlabel('Bird Label')
plt.title('Percentage Classification Accuracy - Genetic CNN')
Out[91]:
Text(0.5, 1.0, 'Percentage Classification Accuracy - Genetic CNN')
In [93]:
model.evaluate(test_generator, use_multiprocessing = True, workers = 10)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_3084\4002429505.py in <module>
----> 1 model.evaluate(test_generator, use_multiprocessing = True, workers = 10)

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py in evaluate(self, x, y, batch_size, verbose, sample_weight, steps, callbacks, max_queue_size, workers, use_multiprocessing, return_dict, **kwargs)
   1499             with tf.profiler.experimental.Trace('test', step_num=step, _r=1):
   1500               callbacks.on_test_batch_begin(step)
-> 1501               tmp_logs = self.test_function(iterator)
   1502               if data_handler.should_sync:
   1503                 context.async_wait()

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    883 
    884       with OptionalXlaContext(self._jit_compile):
--> 885         result = self._call(*args, **kwds)
    886 
    887       new_tracing_count = self.experimental_get_tracing_count()

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    922       # In this case we have not created variables on the first call. So we can
    923       # run the first trace but we should fail if variables are created.
--> 924       results = self._stateful_fn(*args, **kwds)
    925       if self._created_variables and not ALLOW_DYNAMIC_VARIABLE_CREATION:
    926         raise ValueError("Creating variables on a non-first call to a function"

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
   3036     with self._lock:
   3037       (graph_function,
-> 3038        filtered_flat_args) = self._maybe_define_function(args, kwargs)
   3039     return graph_function._call_flat(
   3040         filtered_flat_args, captured_inputs=graph_function.captured_inputs)  # pylint: disable=protected-access

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
   3458               call_context_key in self._function_cache.missed):
   3459             return self._define_function_with_shape_relaxation(
-> 3460                 args, kwargs, flat_args, filtered_flat_args, cache_key_context)
   3461 
   3462           self._function_cache.missed.add(call_context_key)

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _define_function_with_shape_relaxation(self, args, kwargs, flat_args, filtered_flat_args, cache_key_context)
   3380 
   3381     graph_function = self._create_graph_function(
-> 3382         args, kwargs, override_flat_arg_shapes=relaxed_arg_shapes)
   3383     self._function_cache.arg_relaxed[rank_only_cache_key] = graph_function
   3384 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3306             arg_names=arg_names,
   3307             override_flat_arg_shapes=override_flat_arg_shapes,
-> 3308             capture_by_value=self._capture_by_value),
   3309         self._function_attributes,
   3310         function_spec=self.function_spec,

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes, acd_record_initial_resource_uses)
   1005         _, original_func = tf_decorator.unwrap(python_func)
   1006 
-> 1007       func_outputs = python_func(*func_args, **func_kwargs)
   1008 
   1009       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
    666         # the function a weak reference to itself to avoid a reference cycle.
    667         with OptionalXlaContext(compile_with_xla):
--> 668           out = weak_wrapped_fn().__wrapped__(*args, **kwds)
    669         return out
    670 

c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
    992           except Exception as e:  # pylint:disable=broad-except
    993             if hasattr(e, "ag_error_metadata"):
--> 994               raise e.ag_error_metadata.to_exception(e)
    995             else:
    996               raise

ValueError: in user code:

    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:1330 test_function  *
        return step_function(self, iterator)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:1320 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1286 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2849 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3632 _call_for_each_replica
        return fn(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:1313 run_step  **
        outputs = model.test_step(data)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\training.py:1270 test_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\engine\compile_utils.py:201 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:141 __call__
        losses = call_fn(y_true, y_pred)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:245 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\util\dispatch.py:206 wrapper
        return target(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\losses.py:1666 categorical_crossentropy
        y_true, y_pred, from_logits=from_logits, axis=axis)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\util\dispatch.py:206 wrapper
        return target(*args, **kwargs)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\keras\backend.py:4839 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    c:\Users\MAK\anaconda3\envs\myenv\lib\site-packages\tensorflow\python\framework\tensor_shape.py:1161 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, 1) and (None, 250) are incompatible

Bibliographic references

  • https://www.pyimagesearch.com/2018/05/07/multi-label-classification-with-keras/

  • https://medium.com/@1297rohit/transfer-learning-from-scratch-using-keras-339834b153b9

  • Loss_Scarce_Categorical: https://stackoverflow.com/questions/63600431/model-fit-typeerror-nonetype-object-is-not-callable

  • https://www.kaggle.com/pankul/image-classification-w-vgg16-weights

  • https://medium.com/analytics-vidhya/multi-class-classification-using-cnn-for-custom-dataset-7759865bd19

Genetic Algorithm¶

  • https://blog.coast.ai/lets-evolve-a-neural-network-with-a-genetic-algorithm-code-included-8809bece164

  • https://yaron-strauch.com/Evolving%20Convolutional%20Neural%20Network%20Topologies%20for%20Image%20Recognition%20-%20Yaron%20Strauch.pdf

  • https://blog.paperspace.com/train-keras-models-using-genetic-algorithm-with-pygad/